Search Results for author:
Found 3 papers, 0 papers with code
Pose Guided Human Image Synthesis with Partially Decoupled GAN
Most existing methods encode the texture of the whole reference human image into a latent space, and then utilize a decoder to synthesize the image texture of the target pose.
Augmentation-induced Consistency Regularization for Classification
In this paper, we propose a consistency regularization framework based on data augmentation, called CR-Aug, which forces the output distributions of different sub models generated by data augmentation to be consistent with each other.
Improving Human Image Synthesis with Residual Fast Fourier Transformation and Wasserstein Distance
And the second is that the training of GAN is unstable and slow to converge, such as model collapse.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
